CN109359206A

CN109359206A - Image processing method and system based on Internet of Things campus administration

Info

Publication number: CN109359206A
Application number: CN201811206437.5A
Authority: CN
Inventors: 郑称德
Original assignee: Individual
Current assignee: Individual
Priority date: 2018-10-17
Filing date: 2018-10-17
Publication date: 2019-02-19

Abstract

The present invention relates to technical field of Internet information more particularly to a kind of image processing methods and system based on Internet of Things campus administration, and wherein the method carries out piecemeal to image；Each described eigenvector composition characteristic matrix is carried out dimensionality reduction to the eigenmatrix by the feature vector for extracting each block image；The eigenmatrix of dimensionality reduction is matched in feature database, if matching, stores described image.Separation by implementing image hashing and image data with the block chain of the borrow decentralization of anti-tamper characteristic stores, change the data storage technology based on centralization, avoid campus network congestion, storage burden and the risk integrally damaged, it ensure that safety, authenticity and the integrality of image data, and realize the effective query of image data.

Description

Image processing method and system based on Internet of Things campus administration

Technical field

The present invention relates to technical field of Internet information more particularly to a kind of image procossings based on Internet of Things campus administration Method and system.

Background technique

Block chain technology is also referred to as distributed account book technology, is substantially a kind of distributed interconnection data of decentralization Library.Block chain network can be considered using the network of block chain Technical Architecture, include multiple block chain nodes in the block chain network, Either block chain node can correspond at least one block chain, and either block chain may include at least one block.

In the prior art, the application of block chain can be divided into two classes:

Publicly-owned chain: all nodes can participate in common recognition, competition book keeping operation power.Publicly-owned chain is any individual or group towards masses Body can read, send transaction and transaction can obtain effective confirmation of the block chain, participate in the block chain of common recognition.Data are public It opens.Its main feature is that: neutrality, open, transactions velocity is slow, need " digging mine " or similar to common recognition method, commonly uses P2P network, anti-examination Property it is high.

License chain: the node being only licensed could know together, compete book keeping operation power and create block, include privately owned chain, alliance All non-publicly-owned chains such as chain, enterprise's chain.Data can be openly or underground.Wherein, privately owned chain refers to write-in permission in a group Knit the block chain in hand；Alliance's chain refer to by several personal or tissues, company, government control block chain.The characteristics of permitting chain Be: transactions velocity is fast, not needing the whole network common recognition, transaction cost of " digging mine " class, low (transaction only needs several permit nodes verifyings i.e. Can)；It can examine, the mainstream of commercial application field can be occupied.

Specifically, the process of image data cochain (being stored in block chain network) includes three phases:

1, the stage is accepted, it can be understood as the image data to cochain is received by a certain block chain node in block chain network It arrives, and the image data is accepted by the block chain node；

2, it knows together the stage, it can be understood as block chain node needs after accepting the image data by block chain network Other block chain nodes participate in carrying out the image data common recognition processing, after image data is by common recognition, can enter storage rank Section；

3, memory phase, it can be understood as the image data that block chain node passes through common recognition carries out cochain processing.

Common recognition method i.e. common recognition algorithm in block chain technology is realized between different blocks chain node in block chain network Establish the important method for trusting, obtaining equity.So-called common recognition method is the ballot by special joint, in a short period of time The verifying and confirmation of complete swap；To a transaction, if several incoherent nodes of interests can reach common understanding, so that it may To think that the whole network can also reach common understanding to this.A kind of data structure of the block chain as storing data in chronological order, can prop up Hold different common recognition methods.

Under different common recognition methods, the generating process of block can be slightly different.But on the whole, each node is received in processing After the block information arrived, process of exchange is substantially all according to following process: node receives several Transaction Informations, is put into trading pit In；Node obtains the Transaction Information being currently received from trading pit, is ranked up to transaction and executes in order；It is finished it Afterwards, node generates intact block, is finally broadcasted.

Student information storage mode used at present is commonly divided into two classes, and one kind is centralised storage, this mode meeting All student informations are centrally stored in a server, but this storage mode pole when being hacked or breaking down Easily there is a situation where student information is tampered or is damaged, safety is lower；Another kind of is distributed storage, and this mode can will be learned Raw information distribution is stored in multiple servers, namely forms more set backups, effectively improves the safety of information, but by It is that safety is exchanged for redundancy in this mode, in the case where student information is more, a large amount of storage resource can be wasted.

Summary of the invention

In view of the deficiencies of the prior art, the present invention provides a kind of image processing method based on Internet of Things campus administration and System solves the continuous growth existing in the prior art with campus student image data amount, is easy to cause campus network Congestion and storage burden improve storage efficiency to reach to prevent network congestion, save storage quantity, guarantee data security Purpose, concrete scheme is as follows:

In a first aspect, the present invention provides a kind of image processing methods based on Internet of Things campus administration, which comprises

Piecemeal is carried out to image, wherein non-overlapping region between any block image；

The feature vector for extracting each block image, by each described eigenvector composition characteristic matrix, to the eigenmatrix Carry out dimensionality reduction；

The eigenmatrix of dimensionality reduction is matched in feature database, if matching, stores described image.

Preferably, the storage described image, which comprises

Block is generated using described image；

The block is sent to each common recognition node on block chain and carries out common recognition verification；

If verification passes through, the block is added in block chain, and described image is sent to campus databases to store.

It is preferably, described to generate block using described image, which comprises

Hash transformation is carried out to the described image of acquisition, obtains the summary data of image；

With the private key of the corresponding public and private key centering of described image, digital encryption is carried out to the summary data of described image, is obtained The image hashing data of encryption；

The summary data of the summary data of the digital signature of described image and a upper block, described image is packaged into block.

Preferably, the generation method of the public and private key pair, which comprises

According to the feature vector of described image and the random number generated by random number generator, private key is generated, and be based on the private Key generates public key.

It is preferably, described that described image is sent to campus databases to store, which comprises

The mapping relations between the summary data and the image identification of described image are established, according to the mapping relations, by institute Image is stated to store to the campus databases.

Preferably, the method also includes:

The inquiry request to described image is received, determines the summary data of inquired image, and the summary data is corresponding Image returned by the campus databases.

Preferably, before the reception is to the inquiry request of described image, the method also includes: by the block chain Multiple block subchains are divided into, successively request to inquire to the node of each block subchain.

Second aspect, the present invention provides a kind of image processing system based on Internet of Things campus administration, the system packet It includes:

Piecemeal module, for carrying out piecemeal to image, wherein non-overlapping region between any block image；

Processing module is right by each described eigenvector composition characteristic matrix for extracting the feature vector of each block image The eigenmatrix carries out dimensionality reduction；

Matching module, for matching the eigenmatrix of dimensionality reduction in feature database, if matching, stores described image.

The third aspect, the present invention provides a kind of image processing equipment based on Internet of Things campus administration, the equipment packet It includes:

Communication bus, for realizing the connection communication between processor and memory；

Memory, for storing computer program；

Processor, for executing the computer program to realize following steps:

Fourth aspect, the present invention provides a kind of computer readable storage mediums, are stored thereon with computer program, described The method of above-mentioned first aspect is realized when computer program is executed by processor.

Beneficial effects of the present invention: the image processing method and system of the invention based on Internet of Things campus administration passes through Processing to image block, dimensionality reduction, borrow the block chain of decentralization implement the separation of image hashing and image data storage, Change the data storage technology based on centralization.So the embodiment of the present invention has reached following technical effect: solving existing skill With the continuous growth of campus student image data amount present in art, it is easy to cause campus network congestion and storage burden；It keeps away Exempt from integrally to be damaged under the situations such as potential delay machine, operation troubles under the image procossing memory module of traditional centralization Risk；Due to the anti-tamper characteristic that block chain has, thus the storage of image hashing and data separating causes either side can not Storing data is distorted privately, to not only effectively ensure that the safety of image data, but also can guarantee data image Authenticity, the integrality of data, and realize the effective query of image data.

Detailed description of the invention

To describe the technical solutions in the embodiments of the present invention more clearly, make required in being described below to embodiment Attached drawing is briefly described, it should be apparent that, drawings in the following description are only some embodiments of the invention, attached drawing In embodiment do not constitute any limitation of the invention, for those of ordinary skill in the art, do not paying creativeness Under the premise of labour, it is also possible to obtain other drawings based on these drawings.

Fig. 1 is one flow diagram of image processing method embodiment the present invention is based on Internet of Things campus administration.

Fig. 2 is two flow diagram of image processing method embodiment the present invention is based on Internet of Things campus administration.

Fig. 3 is the one embodiment flow diagram of image storage method the present invention is based on Internet of Things campus administration.

Fig. 4 is one example structure schematic diagram of image processing system the present invention is based on Internet of Things campus administration.

Fig. 5 is one example structure schematic diagram of image processing equipment the present invention is based on Internet of Things campus administration.

Specific embodiment

Technical solution of the present invention is described in further detail with embodiment with reference to the accompanying drawing, this be it is of the invention compared with Good embodiment.It should be appreciated that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments； It should be noted that in the absence of conflict, the feature in embodiment and embodiment in the present invention can be combined with each other.Base Embodiment in the present invention, it is obtained by those of ordinary skill in the art without making creative efforts it is all its His embodiment, shall fall within the protection scope of the present invention.

The main thought of technical solution of the embodiment of the present invention: piecemeal is carried out to image, wherein between any block image Non-overlapping region；The feature vector for extracting each block image, by each described eigenvector composition characteristic matrix, to the spy It levies matrix and carries out dimensionality reduction；The eigenmatrix of dimensionality reduction is matched in feature database, if matching, stores described image.

It is right in conjunction with appended figures and specific embodiments in order to better understand above-mentioned technical solution Above-mentioned technical proposal is described in detail.

Embodiment one

One embodiment of the invention provides a kind of image processing method based on Internet of Things campus administration, as shown in Figure 1, with lower section The executing subject of each step is specifically as follows the various equipment with bio-identification function in method embodiment, such as: mobile phone, individual Computer, PAD, access control equipment etc., the image processing method can specifically include following steps:

Step S101 carries out piecemeal to image, wherein non-overlapping region between any block image；

Specifically, piecemeal processing is carried out to original image, original image is divided into several pieces.It can be and preset original graph Picture is divided into the determining block numbers such as 4 pieces, 8 pieces, can also be and determines piecemeal quantity according to the pixel quantity of open ended original image, To carry out piecemeal processing to original image.Wherein, all there is no the regions of overlapping between any block image.In the present invention Apply in embodiment, the method for partition is mainly used in the extraction of facial characteristics, and the image for needing to extract feature is generally Face-image with no restrictions for piecemeal quantity can be specifically arranged according to actual needs.

Step S102 extracts the feature vector of each block image, right by each described eigenvector composition characteristic matrix The eigenmatrix carries out dimensionality reduction；

In the present patent application embodiment, the Advanced method for extracting the feature vector of each block image can be algebra spy Sign, the algebraic characteristic include the information of the scenery in corresponding block image, can be used for subsequent image identification.

In practical applications, when carrying out image block extraction, it usually needs a large amount of image is handled, in the present patent application reality It applies in example, is applied to parallel device, for example, field programmable gate array etc., more to realize by the processing capacity of parallel device The parallel processing that a image block extracts.

Specifically, the method for extracting block image feature may include Fourier transform, window fourier transform method, small Wave conversion method, least square method, edge direction histogram method etc. can be used after above-mentioned various existing methods handle piecemeal and obtain The each block image arrived carries out principal component proper phase matrix and extracts.Such as: it can be using local binary patterns LBP description Extracting method obtains the LBP histogram of each block image, further, can also be according to the LBP histogram of each block image Figure extracts the feature vector of each block image.Alternatively, finding out the mean value of block image, each block image is subtracted into average value Standardized block image is obtained, to each standardized subgraph matrix, covariance matrix is found out, then finds out covariance square The feature vector and characteristic value of battle array.The corresponding feature vector of several preceding maximum characteristic values is chosen, according to each block diagram As the characteristics of find out the weight vectors of each block image.

In practical applications, the dimension of the feature vector for each block image that said extracted goes out is usually very high, subsequent The complexity of matching primitives can be very high, and the corresponding calculating time also can be very long, therefore, in scheme shown in the embodiment of the present disclosure, Each described eigenvector after image processing equipment can be extracted first using block image characterization method forms an eigenmatrix, Dimensionality reduction is carried out to the eigenmatrix again, the dimension of each feature vector is reduced, with reduce subsequent calculating complexity and Calculate the time.

In the present patent application embodiment, image processing equipment can pass through principal component analysis (principal Components analysis, PCA) algorithm to carry out dimension-reduction treatment to the feature vector of each block image.Principal component analysis Algorithm is usually used in reducing the dimension of data set, it is intended to using the thought of dimensionality reduction, multi objective is converted into a few overall target, Particular by low order principal component is retained, ignore high-order principal component, keeps to the maximum feature of variance contribution in data set, it is of equal value In remaining the most important characteristics in data.

Step S103 matches the eigenmatrix of dimensionality reduction in feature database, if matching, stores described image.

Specifically, the Euclidean distance matching degree of the eigenmatrix for traversing dimensionality reduction and the sample data in feature database identifies above-mentioned Image, more specifically, search sample data in the smallest feature database at a distance from the eigenmatrix of above-mentioned dimensionality reduction, judges above-mentioned drop Whether the minimum value of sample data distance is greater than given threshold in the eigenmatrix of dimension and all feature databases, if it has, then matching, The corresponding original image of the eigenmatrix of the dimensionality reduction of dimensionality reduction in this way is recognition result, otherwise, is then judged to no recognition result.

When dimensionality reduction eigenmatrix in feature database sample data match, the eigenmatrix of the dimensionality reduction of dimensionality reduction is corresponding Raw image storage, as shown in figure 3, detailed description is specific as follows:

Step S1031 generates block using described image；

The equipment for accepting image data can be the node of block chain, which can be referred to as service handling node, and initiate To the common recognition of the image data.It can also include multiple nodes, if these nodes participate in the image data other than the node Common recognition processing, then these nodes can be referred to as common recognition node.In addition, these nodes can also be used as service handling section Point.

In the present patent application embodiment, what the node of region chain can be used as image data accepts node, can also not As the node that accepts of image data, and the node as node or this common recognition processing for initiating common recognition processing, this In be not specifically limited.

If the node of region chain accepts node as image data, then the block chain node can be from being locally stored A part of image data is fished in the image data accepted as image data to be known together, in order to subsequent for fishing for The part image data initiates common recognition processing.

If the node of region chain is not as the accepting node of image data and as the node that this common recognition is handled, then should Block chain node can fish for a part of image data as picture number to be known together from image data resource pool to be known together According in order to the subsequent common recognition processing initiated for the part image data fished for.

The type of the node can be individual, enterprise, regulatory agency etc., be also possible to credit is high, in credit, credit it is low Etc. different credit grades.In short, the type of node can divide according to the actual situation, the application is without limitation.

Specifically, its client that can install built-in docking standard agreement at the terminal, so that it may pass through the client Service request is submitted at any time in end.

Specifically, Hash transformation is carried out to the described image of acquisition first, obtains the summary data of image；Then with described The private key of the corresponding public and private key centering of image carries out digital encryption to the summary data of described image, obtains the image of encryption Summary data；Finally the summary data of the summary data of the digital signature of described image and a upper block, described image is sealed Dress up block.

Wherein, the generation method of the public and private key pair is specifically: according to the feature vector of described image and by random number The random number that generator generates generates private key, and generates public key based on the private key.

It should be noted that block chain network can preset a public and private key pair for each student, different students' Private key is different, in this way, block chain node is encrypted the image data of the student using the private key of the student, Neng Goubao Demonstrate,prove the safety of the image data of the student.

The block is sent to each common recognition node on block chain and carries out common recognition verification by step S1032；

Since the user information as block is sent to the common recognition node, so the node is when receiving the transaction data, only To include user information in the transaction data, can determine that the corresponding processing data of the block are accepted by which user side.

It should be noted that the node can be terminal, e.g., mobile phone, PC/tablet computer, tracing terminal etc. are set It is standby, it is also possible to server, then the server can be the corresponding server of the node, and the server can be individual one Platform equipment is also possible to the system being made of multiple devices, if the equipment can be used as the block chain network node receive with The corresponding image data of common recognition node, and there is the permission that common recognition is initiated in the block chain network, the application couple The node be specially which kind of equipment this and without limitation.

For each node, the common recognition checking procedure of the node is specifically: the node can be held with itself Some public keys verify the signing messages for including in the block, after determining the signing messages by verifying, further according to The content for including in the block verifies the head cryptographic Hash of the block.Pass through verifying in the head cryptographic Hash for determining the block Afterwards, then it can determine the block by verifying, i.e., block is verified by block chain.

Wherein, verification code type is configurable to the common Encryption Algorithm of various those skilled in the art or checking algorithm institute The check code of generation.

It should be noted that specifically each node carries out transaction data according to common recognition algorithm in block chain technical field Common recognition verification, also, the privacies such as Account History of each node of block chain network Internet access, for verifying.

The block is added in block chain, and described image is sent to campus by step S1033 if verification passes through Database is to store.

The capacity as shared by image data is bigger, if directly transmitted in block chain network, will reduce block The data-handling efficiency of chain network.Thus, image data is stored in campus databases, in order to prevent these medical data quilts It distorts, the summary data of these image datas is stored in block chain network, once image data is modified, it is meant that modification The summary data of image data afterwards will be different from the summary data of original image data, neither influence block chain network in this way Treatment effeciency, can also guarantee that these image datas are not tampered, and safeguard the authenticity and integrity of image data.

Specifically, the block is added in block chain, the summary data and described image are established if verification passes through Image identification between mapping relations, according to the mapping relations, by described image distributed storage to the campus data Library.In this way, facilitate other block chain nodes when needing the corresponding image data of the summary data, it can be from the block chain node The image data is quickly found in corresponding campus databases.

Step S104 receives the inquiry request to described image, determines the summary data of inquired image, and will be described The corresponding image of summary data is returned by the campus databases.

Specifically, since image data is related to the individual privacy of student, user is being received to the figure of student As data inquiry request when, need to carry out authentication to the user, than such as whether this school parents of student or teacher, if body Part is correct, then compares the finger image for all history image data that the finger image in inquiry request is stored with itself Compared with.If finding identical finger image, shows that the finger image in inquiry request belongs to certain history image data, return to inquiry Success.It can be shown in some or all of the history image data at this time and described image data are perhaps sent to initiation inquiry User.If not finding identical finger image, show that the finger image in inquiry request is not belonging to any history image number According to return inquiry failure.

Described image fingerprint refers to the fingerprint value obtained by image data according to Encryption Algorithm, is unable to reverse push deduced image Whether data are only capable of whether there is for authentication image data and being tampered.For example, hash function can be the application A kind of Encryption Algorithm, but for be specially which kind of Encryption Algorithm this and without limitation, using other Encryption Algorithm also in this hair Within the protection scope of bright application.

It should be noted that the executing subject of each step of the present patent application embodiment institute providing method may each be same Equipment, alternatively, this method is also by distinct device as executing subject.

Embodiment two

One embodiment of the invention provides a kind of image processing method based on Internet of Things campus administration, as shown in Fig. 2, with lower section The executing subject of each step is specifically as follows the various equipment with bio-identification function in method embodiment, such as: mobile phone, individual Computer, PAD, access control equipment etc., the image processing method can specifically include following steps:

Step S201 carries out piecemeal to image, wherein non-overlapping region between any block image；

Step S202 extracts the feature vector of each block image, right by each described eigenvector composition characteristic matrix The eigenmatrix carries out dimensionality reduction；

Step S203 matches the eigenmatrix of dimensionality reduction in feature database, if matching, stores described image.

Step S2031 generates block using described image；

The block is sent to each common recognition node on block chain and carries out common recognition verification by step S2032；

The block is added in block chain, and described image is sent to campus by step S2033 if verification passes through Database is to store.

The block chain is divided into multiple block subchains by step S204, is successively asked to the node of each block subchain Ask inquiry；

In order to improve search efficiency, the block chain is divided into multiple block subchains, is asked to the node of each block subchain Ask inquiry.

Specifically, block chain is divided into multiple block subchains that length is 256, successively each block is inquired in traversal request Chain, the queue number of the block of each block subchain is 1-256,257-512,513-768 ..., etc..

In an alternative embodiment, also it can set other different big for the length of block subchain according to actual needs Small regular length or variable-length.

Step S205 receives the inquiry request to described image, determines the summary data of inquired image, and will be described The corresponding image of summary data is returned by the campus databases.

Embodiment three

One embodiment of the invention provides a kind of image processing system based on Internet of Things campus administration, in the embodiment of the present invention In, the information transmission system in the present embodiment is the specific master for executing the above-mentioned image processing method based on Internet of Things campus administration Body, as shown in figure 4, the information transmission system can specifically include following module:

Example IV

One embodiment of the invention provides a kind of image processing equipment based on Internet of Things campus administration, as shown in figure 5, the information Pushing equipment can specifically include following module:

Memory, for storing computer program；Memory may include high speed RAM memory, it is also possible to also include non-shakiness Fixed memory (non-volatile memory), for example, at least a magnetic disk storage.Memory optionally may include to A few storage device.

Processor, for executing above-mentioned computer program to realize following steps:

Step S301 carries out piecemeal to image, wherein non-overlapping region between any block image；

Step S302 extracts the feature vector of each block image, right by each described eigenvector composition characteristic matrix The eigenmatrix carries out dimensionality reduction；

Step S303 matches the eigenmatrix of dimensionality reduction in feature database, if matching, stores described image.

When dimensionality reduction eigenmatrix in feature database sample data match, the eigenmatrix of the dimensionality reduction of dimensionality reduction is corresponding Raw image storage is described in detail specific as follows:

Step S3031 generates block using described image；

The block is sent to each common recognition node on block chain and carries out common recognition verification by step S3032；

The block is added in block chain, and described image is sent to campus by step S3033 if verification passes through Database is to store.

The block chain is divided into multiple block subchains by step S304, is successively asked to the node of each block subchain Ask inquiry；

Step S305 receives the inquiry request to described image, determines the summary data of inquired image, and will be described The corresponding image of summary data is returned by the campus databases.

Processor in the present embodiment may be a kind of IC chip, have signal handling capacity.In the process of realization In, each step of the above method can be complete by the integrated logic circuit of the hardware in processor or the instruction of software form At.Above-mentioned processor can be general processor, digital signal processor (DSP), specific integrated circuit (ASIC), it is ready-made can Program gate array (FPGA) either other programmable logic device, discrete gate or transistor logic, discrete hardware components. It may be implemented or execute disclosed each method, step and the logic diagram in the embodiment of the present invention.Above-mentioned processor can be Microprocessor or above-mentioned processor are also possible to any conventional processor etc..The method in conjunction with disclosed in the embodiment of the present invention The step of can be embodied directly in hardware processor and execute completion, or in processor hardware and software module combination execute It completes.Software module can be located at random access memory, flash memory, read-only memory, programmable read only memory or electrically-erasable In the storage medium of this fields such as programmable storage, register maturation.The storage medium is located at memory, and processor reading is deposited Information in reservoir, in conjunction with the step of its hardware completion above method.

Embodiment five

One embodiment of the invention provides a kind of computer readable storage medium, is stored thereon with computer program, above-mentioned calculating Machine program realizes the above-mentioned image processing method based on Internet of Things campus administration when being executed by processor.

It is to sum up above-mentioned, a kind of image processing method based on based on Internet of Things campus administration provided in an embodiment of the present invention and System borrows the block chain of decentralization by the processing to image block, dimensionality reduction to implement image hashing and image data Separation storage, changes the data storage technology based on centralization.So the embodiment of the present invention has reached following technical effect: The continuous growth existing in the prior art with campus student image data amount is solved, campus network congestion is easy to cause and is deposited Storage burden；Avoid under the image procossing memory module of traditional centralization quilt under the situations such as potential delay machine, operation troubles The risk integrally damaged；Due to the anti-tamper characteristic that block chain has, thus the storage of image hashing and data separating causes to appoint The side that anticipates can not privately distort storing data, to not only effectively ensure that the safety of image data, but also can guarantee The data authenticity of image data, integrality, and realize the effective query of image data.

It should be noted that for the various method embodiments described above, for simple description, therefore, it is stated as a series of Combination of actions, but those skilled in the art should understand that, the present invention is not limited by the sequence of acts described because According to the present invention, some steps may be performed in other sequences or simultaneously.Secondly, those skilled in the art should also know It knows, embodiment described in this description belongs to alternative embodiment, and related actions and modules is not necessarily of the invention It is necessary.

Above-described embodiment can be realized wholly or partly by software, hardware, firmware or any other combination.When When using software realization, above-described embodiment can be realized entirely or partly in the form of a computer program product.The computer Program product includes one or more computer instructions.When loading or execute on computers the computer program instructions, all Or partly generate the process or function being somebody's turn to do according to the embodiment of the present application.The computer can be general purpose computer, dedicated computing Machine, computer network or other programmable devices.The computer instruction may be stored in a computer readable storage medium, Or transmitted from a computer readable storage medium to another computer readable storage medium, for example, the computer instruction Wired (such as infrared, wireless, microwave etc.) mode can be passed through from a web-site, computer, server or data center It is transmitted to another web-site, computer, server or data center.The computer readable storage medium can be meter Any usable medium that calculation machine can access either includes server, the data center etc. of one or more usable medium set Data storage device.The usable medium can be magnetic medium (for example, floppy disk, hard disk, tape), optical medium (for example, DVD), Or semiconductor medium.Semiconductor medium can be solid state hard disk.

Those of ordinary skill in the art may be aware that list described in conjunction with the examples disclosed in the embodiments of the present disclosure Member and algorithm steps can be realized with the combination of electronic hardware or computer software and electronic hardware.These functions are actually It is implemented in hardware or software, the specific application and design constraint depending on technical solution.Professional technician Each specific application can be used different methods to achieve the described function, but this realization is it is not considered that exceed Scope of the present application.

In the above-described embodiments, it all emphasizes particularly on different fields to the description of each embodiment, there is no the portion being described in detail in some embodiment Point, reference can be made to the related descriptions of other embodiments.

It is apparent to those skilled in the art that for convenience and simplicity of description, the system of foregoing description, The specific work process of device and unit, can refer to corresponding processes in the foregoing method embodiment, and details are not described herein.

In several embodiments provided by the present invention, it should be understood that disclosed system, device and method can be with It realizes by another way.For example, the apparatus embodiments described above are merely exemplary, for example, the unit It divides, only a kind of logical function partition, there may be another division manner in actual implementation, such as multiple units or components It can be combined or can be integrated into another system, or some features can be ignored or not executed.Another point, it is shown or The mutual coupling, direct-coupling or communication connection discussed can be through some interfaces, the indirect coupling of device or unit It closes or communicates to connect, can be electrical property, mechanical or other forms.

The unit as illustrated by the separation member may or may not be physically separated, aobvious as unit The component shown may or may not be physical unit, it can and it is in one place, or may be distributed over multiple In network unit.It can select some or all of unit therein according to the actual needs to realize the mesh of this embodiment scheme 's.

It, can also be in addition, the functional units in various embodiments of the present invention may be integrated into one processing unit It is that each unit physically exists alone, can also be integrated in one unit with two or more units.Above-mentioned integrated list Member both can take the form of hardware realization, can also realize in the form of software functional units.

If the integrated unit is realized in the form of SFU software functional unit and sells or use as independent product When, it can store in a computer readable storage medium.Based on this understanding, technical solution of the present invention is substantially The all or part of the part that contributes to existing technology or the technical solution can be in the form of software products in other words It embodies, which is stored in a storage medium, including some instructions are used so that a computer Equipment (can be personal computer, server or the network equipment etc.) executes each embodiment the method for the present invention All or part of the steps.And storage medium above-mentioned includes: USB flash disk, mobile hard disk, read-only memory (read-only Memory, ROM), random access memory (random access memory, RAM), magnetic or disk etc. is various to deposit Store up the medium of program code.

The present invention be referring to the embodiment of the present invention method, apparatus (equipment) and computer program product flow chart with/ Or block diagram describes.It should be understood that each process that can be realized by computer program instructions in flowchart and/or the block diagram and/ Or the combination of the process and/or box in box and flowchart and/or the block diagram.It can provide these computer program instructions To general purpose computer, special purpose computer, Embedded Processor or other programmable data processing devices processor to generate one A machine so that by the instruction that the processor of computer or other programmable data processing devices executes generate for realizing The device for the function of being specified in one or more flows of the flowchart and/or one or more blocks of the block diagram.

These computer program instructions, which may also be stored in, is able to guide computer or other programmable data processing devices with spy Determine in the computer-readable memory that mode works, so that it includes referring to that instruction stored in the computer readable memory, which generates, Enable the manufacture of device, the command device realize in one box of one or more flows of the flowchart and/or block diagram or The function of being specified in multiple boxes.

These computer program instructions also can be loaded onto a computer or other programmable data processing device, so that counting Series of operation steps are executed on calculation machine or other programmable devices to generate computer implemented processing, thus in computer or The instruction executed on other programmable devices is provided for realizing in one or more flows of the flowchart and/or block diagram one The step of function of being specified in a box or multiple boxes.

It should be noted that, in this document, relational terms such as first and second and the like are used merely to a reality Body or operation are distinguished with another entity or operation, are deposited without necessarily requiring or implying between these entities or operation In any actual relationship or order or sequence.Moreover, the terms "include", "comprise" or its any other variant are intended to Non-exclusive inclusion, so that the process, method, article or equipment including a series of elements is not only wanted including those Element, but also including other elements that are not explicitly listed, or further include for this process, method, article or equipment Intrinsic element.In the absence of more restrictions, the element limited by sentence "including a ...", it is not excluded that There is also other identical elements in process, method, article or equipment including the element.

Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention., rather than its limitations；To the greatest extent Pipe present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that: its according to So be possible to modify the technical solutions described in the foregoing embodiments, or to some or all of the technical features into Row equivalent replacement；And these are modified or replaceed, various embodiments of the present invention technology that it does not separate the essence of the corresponding technical solution The range of scheme.

Claims

1. a kind of image processing method based on Internet of Things campus administration, which is characterized in that the described method includes:

2. the method according to claim 1, wherein the storage described image, which comprises

Block is generated using described image；

3. according to the method described in claim 2, it is characterized in that, described generate block, the method packet using described image It includes:

4. according to the method described in claim 3, it is characterized in that, the generation method of the public and private key pair, the method packet It includes:

5. according to the method described in claim 3, it is characterized in that, described be sent to campus databases for described image to deposit Storage, which comprises

6. method according to claim 1-5, which is characterized in that the method also includes:

7. according to the method described in claim 6, it is characterized in that, it is described reception to the inquiry request of described image before, The method also includes: the block chain is divided into multiple block subchains, is successively requested to the node of each block subchain Inquiry.

8. a kind of image processing system based on Internet of Things campus administration characterized by comprising

Piecemeal module, the image for will acquire carry out piecemeal, extract the feature of each picture frame of described image；

Processing module carries out duplicate removal processing for the feature to each picture frame, and by each spy after duplicate removal processing Sign is cascaded as the feature vector of described image；

Identification module, for described eigenvector to be matched in characteristics of image library, if matching, stores described image.

9. a kind of image processing equipment based on Internet of Things campus administration characterized by comprising

Memory, for storing computer program；

Processor, for executing the computer program to realize following steps:

The image that will acquire carries out piecemeal, extracts the feature of each picture frame of described image；

Duplicate removal processing is carried out to the feature of each picture frame, and each feature after duplicate removal processing is cascaded as the figure The feature vector of picture；

Described eigenvector is matched in characteristics of image library, if matching, stores described image.

10. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that the computer program The method according to claim 1 to 7 is realized when being executed by processor.